OpenClaw Dashboard

实时监控多个AI Agent的运行状态和Token消耗，支持会话列表和飞书群组富文本状态推送。

This skill appears to do what it says: it runs the local `openclaw status` command, parses results, builds a dashboard and a Feishu card payload. It does not request credentials or make outbound network calls itself (the Feishu payload is constructed but not sent by the included code). Before installing: 1) verify that your OpenClaw environment provides the expected Feishu channel integration (since the skill assumes the platform will perform the push), 2) manually inspect SKILL.md for hidden Unicode/control characters (the scanner flagged this), and 3) run the skill in a non-production environment first to confirm its parsing and outputs behave as you expect. If you need the skill to actually send Feishu messages from the local host, expect to provide channel/token configuration separately and audit any code that would perform HTTP requests.

Type: OpenClaw Skill Name: xc-openclaw-dashboard Version: 1.0.0 The skill bundle implements a monitoring dashboard for OpenClaw by executing system commands. The primary indicator is the use of 'child_process.execSync' in 'scripts/collector.js' to run 'openclaw status', which is a high-risk capability (shell access) even though it is plausibly needed for the stated purpose. The skill also collects system metadata such as the computer name and OS version to populate the dashboard. No evidence of intentional malice, prompt injection, or unauthorized data exfiltration was found.